INDEX

Explanations

names related to locations, particularly with historical or natural significance

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

backer

-0.92

ĸļ

-0.89

hood

-0.83

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.81

 Dare

-0.81

 Stur

-0.80

 Burk

-0.79

 Shutterstock

-0.79

ãĥĥãĥĪ

-0.77

Bir

-0.74

POSITIVE LOGITS

oustic

1.45

rylic

1.41

rosse

1.39

rament

1.32

celer

1.26

rete

1.25

ounter

1.24

ademic

1.22

ulum

1.21

acia

1.18

Activations Density 9.347%

names related to locations, particularly with historical or natural significance

No Comments

No Known Activations